{"id":"W2092922846","doi":"10.1145/2344416.2344418","title":"Extracting information networks from the blogosphere","year":2012,"lang":"en","type":"article","venue":"ACM Transactions on the Web","topic":"Topic Modeling","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Benchmark (surveying); Relationship extraction; Task (project management); Information extraction; Pruning; Blogosphere; Weighting; Cluster analysis; Data mining; Information retrieval; Relation (database); Filter (signal processing); Artificial intelligence; The Internet; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007088035,0.001153925,0.0006520719,0.01093037,0.00074613,0.001806471,0.0005914315,0.0007644632,0.001286737],"category_scores_gemma":[0.005866848,0.000401149,0.0006285653,0.00897022,0.0003814068,0.003812918,0.00121469,0.0005540692,0.001387805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005724587,"about_ca_system_score_gemma":0.0007969987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003328313,"about_ca_topic_score_gemma":0.006778314,"domain_scores_codex":[0.9993223,0.0001292935,0.00006362869,0.0001617475,0.0002326698,0.00009041857],"domain_scores_gemma":[0.9967909,0.001908762,0.0004370979,0.000331485,0.0004217471,0.0001099903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004534324,0.0003172165,0.04104189,0.00224742,0.0002407567,0.001824728,0.001459956,0.04255338,0.04130438,0.02142651,0.03612445,0.811006],"study_design_scores_gemma":[0.00007332953,0.0002483355,0.06793076,0.0005143509,0.0003665563,0.002457115,0.002736456,0.5438445,0.0662845,0.1237928,0.1915824,0.0001689979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3850788,0.008543748,0.5388272,0.001791624,0.0003834404,0.0004836392,0.03487159,0.007252821,0.02276715],"genre_scores_gemma":[0.5628505,0.005856538,0.3730576,0.000182746,0.0004883141,0.0003912116,0.05069979,0.000495005,0.005978328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01093037,"threshold_uncertainty_score":0.006617904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02516296794897443,"score_gpt":0.2268239240225655,"score_spread":0.2016609560735911,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}